All AI models in one place
Explore every AI model available in OpenCreator. Compare capabilities, credits per generation and find the best fit for your workflows.
Model pricing and availability are powered directly by the internal configuration, so this page always reflects the latest changes.
Special & Coming Soon
These models may not appear in the default list (e.g. special cases or prelaunch pages).
10 models
Kling O1
Unified multimodal video model (live) with flexible duration and video editing.
Kling Motion Control
Transfer motion from reference video to any subject. Standard & Pro tiers available.
Luma Ray3
Next-generation reasoning video model. Prelaunch page.
Luma Ray3 Modify
Performance-preserving video-to-video workflow. Prelaunch page.
Runway Gen-4.5
Next-gen video generation with stronger motion. Prelaunch page.
FLUX.2
Multi-reference consistency, better text rendering, native image editing. Pro/Turbo/Dev tiers.
Seedance 1.5 Pro
Native audio-video generation with tight lip-sync. Prelaunch page for upcoming availability.
Seedance 2.0
Multimodal video model with image/video/audio/text references, @-material control, and timeline extension/editing.
Kling 2.6 4K
4K/60fps ultra HD video with custom voice library. Coming Q1 2026.
Seedream 5.0
Next-gen ByteDance image model with enhanced consistency and resolution.
Text models
General-purpose reasoning, writing and analysis models.
8 models
Gemini 3 Pro
Most advanced reasoning model ever.
Gemini 3 Flash
Fast and efficient with strong reasoning
Gemini 2.0 Flash
Fast, versatile, strong reasoning
GPT 5.2 Pro
Built for depth, precision, and demanding workflows.
GPT 5.2
Built for speed, efficiency, and scale.
GPT 5
OpenAI's newest flagship model
GPT 4o
Powerful, fast, versatile for all scenarios
GPT 4o Mini
Cost-efficient, intelligent, small model
Image generation
Text-to-image and photo generation models.
15 models
Banana Pro
The world's strongest image editing model.
Nano Banana
Google's new state-of-the-art model
Nano Banana 2
Google's fast image generation and editing model
Imagen 4
Lifelike, composition & color accuracy
GPT Image 1.5
High-quality generation with dynamic pricing by size & quality.
GPT Image 1
Precise, flexible, image diversity
Grok Imagine
Stunning visuals with rich aesthetics
Flux 2 Pro
Zero-config professional image generation
Flux 1.1 Pro
Super fast, image diversity
Seedream 5.0
Next generation image model with web search and multi-turn editing - Coming Soon
Seedream 5.0 Lite
Fast, high quality text-to-image generation by Bytedance.
Seedream 4.5
High-quality image generation with flexible image sizes.
Seedream 4.0
Integrates image generation and editing functions.
Hailuo Image 01
Latest, cinematic, emotional expression
SDXL Fast
Speed of light, versatile
Image editing
Image-to-image and editing focused models.
14 models
Banana Pro
The world's strongest image editing model.
Nano Banana
Google new state-of-the-art model
Nano Banana 2
Google's fast image editing model
GPT Image 1.5
Image editing with dynamic pricing by size & quality.
GPT Image 1
Precise, flexible, image diversity
Flux Kontext
Precise, scene-level editing
Flux 2 Pro
Exceptional photorealism and artistic editing
Gemini 2.0 Flash
Realistic, detailed, accurate
Qwen Image Edit
Superior text editing
Seedream 5.0
Next generation image editing with web search and multi-turn editing - Coming Soon
Seedream 5.0 Lite
Fast, high quality image editing by Bytedance.
Seedream 4.5
Image editing with flexible image sizes.
Seedream 4.0
Integrates image generation and editing functions.
Grok Imagine
Accurate editing with style preservation
Image to video
Image-to-video models for cinematic clips and ads.
28 models
Sora 2
OpenAI's most advanced video model
Sora 2 Pro
Advanced version of Sora 2, with 1080p quality
Veo 3.1 Fast
Advanced AI video with sound
Veo 3.1
Advanced AI video with sound
Veo 3 Fast
Faster & more cost effective Veo 3
Veo 3
Lifelike quality, immersive soundtrack
Veo 2
Expensive but worth it, from Google
Kling 3.0 Standard
Kling 3.0 Standard image-to-video (native audio optional)
Kling 3.0 Pro
Kling 3.0 Pro image-to-video with cinematic visuals (native audio optional)
Kling o3 Standard
Kling o3 image-to-video with start/end frame control
Kling o3 Pro
Kling o3 Pro image-to-video with start/end frame control
Kling 2.6 Pro
Kling's latest Pro model
Kling 2.5 Pro
Professional mode, motion dynamics
Kling 2.1 Pro
Professional mode, motion dynamics
Kling 1.6
High quality, complex scenes
Seedance 1.0 Lite
Lightweight, fast video generation
Seedance 1.5 Pro
Advanced multi-shot video with first-last frame control
Seedance 2.0
Next generation video model - Coming Soon
Hailuo Video 2.3 Pro
Advanced cinematic video generation
Hailuo Video 02
Super realistic, cinematic
Wan 2.6
Latest Wan model, enhanced quality & flexible parameters
Wan 2.5
Latest Wan model, enhanced quality
Wan 2.2
High quality image to video generation
Vidu Q3
Image to video with audio generation support
Runway Gen-4
Super fast, cinematic
Luma Ray 2
Fast, realistic visuals, natural motion
Grok Imagine Video
Cinematic video with immersive audio
Text to video
Text-to-video models for scripts and storyboards.
17 models
Sora 2
OpenAI's most advanced video model
Sora 2 Pro
Advanced version of Sora 2, with 1080p quality
Veo 3.1 Fast
Advanced Al video with sound
Veo 3.1
Advanced Al video with sound
Veo 3 Fast
Faster & more cost effective Veo 3
Veo 3
Lifelike quality, immersive soundtrack
Kling o3 Pro
Kling o3 Pro text-to-video with realistic video generation
Kling 3.0 Pro
Kling 3.0 Pro text-to-video with cinematic visuals (native audio optional)
Kling 3.0 Standard
Kling 3.0 Standard text-to-video with cinematic visuals (native audio optional)
Kling 2.6 Pro
Kling's latest Pro text-to-video model
Wan 2.6
Latest Wan model, enhanced quality & flexible parameters
Vidu Q3
Latest Vidu model with audio generation support
Hailuo Video 02
Super realistic, cinematic
Seedance 1.0 Lite
Lightweight, fast video generation
Seedance 1.5 Pro
Advanced AI video generation from text
Seedance 2.0
Next generation text-to-video - Coming Soon
Grok Imagine Video
Vivid storytelling with built-in soundtrack
Describe image
Vision-language models to understand and describe images.
4 models
Gemini 3 Pro
Most advanced reasoning model ever.
GPT 4o
Powerful, fast, versatile for all scenarios
GPT 5 Mini
Faster, more efficient version of GPT 5
GPT 5
OpenAI's newest flagship model
Image angle control
Multi-view synthesis models that generate new angles from a single photo.
1 model
Qwen Image Edit Multiple Angles
Generate the same scene from new angles
Video lip sync
Models that sync lip motion to speech audio.
2 models
Pixverse Lipsync
Realistic, high quality lipsync model
Sync. Lipsync 2.0
Fast, high quality lipsync model